AI Screenshot Insights for Jira User Documentation

Welcome to AI Screenshot Insights for Jira - User Documentation

Introduction

Recognize your screenshots and streamlines teamwork so you can focus on your more essential tasks at hand rather than retyping the meeting's presentation screenshot.

Welcome to the innovative world of AI Screenshot Insights for Jira! Unleash the power of text extraction and witness the magic as we bring hidden words from attachments to life with just a swish and flick! 🧙‍♂️✨

 

Getting Started

To make it happen, simply install AI Screenshot Insights for Jira on your Atlassian platform by following these simple steps:

  • Search for applicationAI Screenshot Insights for Jira in the Atlassian Marketplace.

  • Install AI Screenshot Insights for Jira into your Jira Software Cloud environment.

  • in your Project's Issue the AI Screenshot Insights button will be shown, click it to start up the application

 

Once you've installed AI Screenshot Insights for Jira into your workspace, it will weave its magic, ready to reveal the secrets hidden within image attachments!

Issue panel with AI Screenshot Insights for Jira

 

 

 

Extracting Text from Attachments

With a simple click, AI Screenshot Insights swiftly extracts text from attachments, unveiling their contents with the help of advanced AI techniques. With more than 160 languages in mind there should be no problem to do the magic including text lines with mixed languages.

Images are loaded from issue attachments when you open the app (issue).

To see newly added images, attachments hit the Reload Attachments button. 🚀

Click to extract text

 

 

Entity Extraction

AI Screenshot Insights for Jira now comes equipped with advanced Named Entity extraction powered by advanced AI techniques. This feature enhances the text extraction process by identifying and categorizing entities such as Person, Skill, Location, URL, and more from the extracted text.

How It Works

When text is extracted from an image, the app then analyzes the text and identifies named entities within it. These entities are then displayed alongside the extracted text in the result area, providing valuable information at a glance.

Configuration

To tailor the Named Entity extraction feature to your needs, you can customize its behavior in the app settings page. Here are some configurable options:

  • Language: Set the language for the entity extraction process.

  • Confidence Score: Decides what level of certainty an extracted entity must meet to be considered valid. It helps control the accuracy of the extraction process.

  • Maximum Data Extraction: Specify the maximum amount of data for each category to be extracted from the text.

  • Entity Categories: Choose from predefined categories of entities for extraction.

Enhancing Your Workflow

This new addition allows you to quickly spot and utilize specific entities within the extracted text. Whether you're looking for a URL, identifying skills, or other entities, Named Entity extraction streamlines your workflow and makes information retrieval more efficient.

Updating Text in the Text Area

When the text is extracted, you will get to edit the text.

The text area serves as your canvas, allowing you to fine-tune the extracted content according to your needs. In some cases, the extracted text may not be 100% accurate, despite the AI powerful capabilities.
The text area enables you to make necessary adjustments for the best possible results before further processing the content in your own way.

Saving as a Comment

Save your thoughts with a professional touch by saving the edited text from the screenshot as a comment for later reference with your colleagues. Share your insights with colleagues as simple as possible 🗨️📋

Use Cases

Multilingual Collaboration

  • Collaboration can involve team members who speak different languages. If someone adds an image with text in a different language, the app can extract and display text, which then can be easily translated.

  • This promotes collaboration across language barriers and encourages global teamwork.

Improved Bug Reporting

  • In software development, bug reports are often accompanied by screenshots or images that illustrate the issues. With this app, testers can upload images, and the text extracted from them provides additional context for developers.

  • Developers can easily copy error messages or log details from the extracted text, leading to faster bug resolution.

Collaborative Brainstorming

  • During brainstorming sessions, teams may sketch diagrams or jot down ideas on a whiteboard. With this app, a quick snapshot of the whiteboard can be uploaded, and the extracted text can be used to structure and categorize ideas within Jira.

  • This fosters innovation by preserving and organizing brainstorming outcomes.

Collaborative Documentation

  • Users can collaborate on documentation within Jira issues. If someone uploads an image containing information relevant to the documentation, the text extracted from the image becomes immediately available for all collaborators.

  • This streamlines the process of adding content, making the documentation more accurate and efficient. Multiple team members can contribute without manual transcription.

Handling Visual Data

  • In data analysis or research projects, there are often visual representations of data or charts. This app can easily extract labels and annotations from charts and make them accessible for team members.

  • Teams can discuss insights more effectively, driving thoughtful analysis and collaboration.

Enhanced Workflow Efficiency

  • Whether it's extracting URLs from an image filled with numerous links or pinpointing key data points, the app facilitates quick information retrieval.

  • Improve productivity by reducing the time spent searching for relevant details, ultimately enhancing your overall work efficiency.

Troubleshooting

🖼️ To guarantee a successful enchantment, ensure that each image attachment does not exceed a size of 16MB. Bigger might seem better, but within this limit lies the sweet spot for flawless processing and impeccable analysis. Embrace the magic of resizing or compressing larger images to unleash their full potential!

AI Screenshot Insights currently focuses on text extraction from image attachments only such as screenshots in PNG or JPG, JPEG. Keep in mind, for now, PDF attachments are outside the scope of our magic. For PDF documents, consider alternative methods of handling text-based content. 📜🔍

Data, privacy, and security

Azure AI Services

The main building blocks of this app are Azure AI Vision algorithms that can analyze visual content and Azure AI Language algorithms that can extract named entities out of the text.
Security has always been a top priority in this matter. That is why we chose to use the Microsoft Azure AI services.

Responsible and trusted Microsoft AI

Microsoft follow and outlines six key principles for responsible AI: accountability, inclusiveness, reliability and safety, fairness, transparency, and privacy and security. These principles are essential to creating responsible and trustworthy AI as it moves into mainstream products and services.

Specific details for each key principle you can find at: Responsible and trusted AI
Microsoft Responsible AI Standard: General Requirements

Certificates

Azure Vision Services hold security certifications (CSA STAR Certification, HIPAA BAA, HITRUST and many more) highlighting the service's security measures.

Authenticate

The most common way to authenticate access to the Image/Text Analysis (Azure Vision/Language services) is by using an API key. Each request to the service URL must include an authentication header. This header passes along an API key, which is used to validate the subscription for this service.

Secure data in transit

The AI services API endpoints use HTTPS URLs for encrypting data during transit. The incoming data is processed in the same region where the Azure resource was created.

Data residency

By default geolocation of the AI Screenshot Insights data center is in the West Europe region.

Azure Private Endpoints

Welcome to the new feature in AI Screenshot Insights for Jira! As we are aware of your security concerns, this addition lets you take control of your AI services. You can deploy your own AI services right into your Azure environment and connect it with our AI Screenshot Insights app, ensuring that image and text processing happens within your own infrastructure.

Why Use Azure Private Endpoints?

Your own private Azure AI services endpoints gives you more control and privacy. No need to send your data to our external endpoints - keep it all within your Azure account.

How to Set it Up

  • Accessing Azure Portal

  • Deploying Azure AI Services

    • Prior to configuring AI Screenshot Insights, deploy your Azure AI services within the Azure Portal.

    • Look for the Computer Vision service (for image analysis) and the Language service (for named entity recognition) and create (deploy) your resources.

  • Locating Keys and Access Tokens

    • In the Azure Portal, locate your deployed AI services.

    • Find the keys and endpoints URLs within the configuration settings of your AI services. These credentials are essential for connecting with the AI Screenshot Insights app.

    • Note: The pictures above illustrate how to access the Computer Vision service (resource) and its settings in Azure portal to obtain the access key and endpoint URL. The same procedure applies to the Language service.

  • Configuring AI Screenshot Insights

    • Open the AI Screenshot Insights configuration settings in Jira.

    • Navigate to the Azure Private Endpoints section.

    • Enter the acquired keys and access tokens in the provided fields for both of the services.

    • Save the configurations to establish a secure connection with your private Azure AI services.

By following these steps, you ensure a secure and private environment for processing images and extracting text within your trusted Azure infrastructure.

AI Screenshot Insights Azure Application

Our Azure application brings you a simplified and streamlined way to deploy and manage the AI services for your Forge application. No need to navigate complex settings as mentioned above – deploy our app effortlessly and unlock the power of AI Screenshots Insights within your own Azure infrastructure.

Benefits

Our app offers a seamless and user-friendly interface for deploying this complex solution. Just input the required parameters in a form, click to deploy, and voila – it eliminates concerns about deployment mistakes. It takes care of the entire lifecycle, including updates and patching, allowing you to focus on your tasks hassle-free. This not only can enhance security but also reduces the risk of accidental resource changes. Managing the cost of Azure resources can be challenging, but this app simplifies it, ensuring smooth budget management.

Now that we understand the benefits, let's move on to the prerequisites for deploying our AI Screenshots Insights Azure Application.

Prerequisites 🪄

If you have deployed any Azure AI service before you may skip following steps.

1. Register the Cognitive Services Resource Provider

Azure Resource Providers are services that provide Azure resources. Before you can create a Cognitive Services resource (which is a service we do use in our solution), you need to ensure that the Cognitive Services Resource Provider is registered.

Check, Register Through Azure Portal
Note: To register a resource provider, you must have the Microsoft.Authorization/register/action permission. This permission is included in the built-in roles for Owner, User Access Administrator. The Contributor role does not have this permission.

  1. Sign in to the Azure portal.

  2. In the left-hand menu, click on "Resource groups".

  3. Select your resource group.

  4. Click on "Settings" > "Resource providers".

  5. In the list of resource providers, look for "Microsoft.CognitiveServices".

  6. If the status of "Microsoft.CognitiveServices" is "NotRegistered", click on "Register".

2. Deploy a Test AI Service to Accept the Responsible AI Notice

When you create a Cognitive Services resource for the first time (or actually any AI service), you need to accept the Responsible AI notice. This notice outlines Microsoft's guidelines and expectations for using AI responsibly.

  1. In the Azure portal, click on "Create a resource".

  2. Search for "Cognitive Services" and click on "Create".

  3. Fill in the required information and click on "Review + create".

  4. You will see the Responsible AI terms notice. Read the notice and click on "Accept" to accept the terms.

Note: After you have accepted the RAI notice, you can delete the test AI service. The acceptance of the RAI notice is tied to your account, not to the specific Cognitive Services resource.

After you have completed these steps, you can proceed with deploying the AI Screenshot Insight Azure application.

Using the Azure application

Follow these steps to integrate the deployed application into JIRA AI Screenshot Insights.

  • Accessing Azure Portal

  • Finding your deployed AI Screenshot Insights application

    • Getting to application’s resources

  • Locating Keys and Access Tokens

    • Works the same for both services (see above)

  • Configuring AI Screenshot Insights

    • Open the AI Screenshot Insights configuration settings in Jira.

    • Navigate to the Azure Private Endpoints section.

    • Enter the acquired keys and access tokens in the provided fields for both of the services.

    • Save the configurations to establish a secure connection with your private Azure AI services.

FAQ

What data is stored within this application?

We understand how important ensuring the security of your sensitive information is to your organisation, thus no user or company related data within this application is being stored.

What happens with my data leaving the Atlassian environment?

The images you submit to extract the text from are processed in real time by the image analysis service, and the input images and results are not retained or stored in the service after processing.

Data (text to analyze) may be generally temporarily stored by Azure AI Language for up to 48 hours only and is purged thereafter. To prevent this temporary storage of input data, the parameter behind it is set to be false for Named Entity Recognition endpoints (which this app uses).

You can find more at: https://learn.microsoft.com/en-us/legal/cognitive-services/computer-vision/imageanalysis-data-privacy-security?context=%2Fazure%2Fai-services%2Fcomputer-vision%2Fcontext%2Fcontext
You can find more at: https://learn.microsoft.com/en-us/legal/cognitive-services/language-service/data-privacy?context=%2Fazure%2Fai-services%2Flanguage-service%2Fcontext%2Fcontext

Feedback and Support

Your invaluable feedback fuels the evolution of AI Screenshot Insights for Jira. Share your insights, and together, we'll cultivate a more refined and impactful user experience! 📊🌱

Our channels are always open to hear from you! If you encounter any challenges or have questions about AI Screenshot Insights for Jira, don't hesitate to reach out to us at our email: support@sykorait.com or via a ticket on our portal: https://support.sykorait.com. 📧